learn
01Skill Claude CodeCodex
Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.
not rated 346
+1 today A SkillSpector: warn 23 tokens
original MIT
brainstorm
02Skill Codex
Explore an ambiguous idea with the user, settle scope and success criteria, and produce an independently reviewed design for wish.
not rated 346
+1
changed 13d ago A SkillSpector: pass 26 tokens
original MIT
council
03Skill Codex
Assess a proposal through independent technical, product, risk, and dissenting lenses, then synthesize a decision without mutating unless explicitly requested.
not rated 346
+1
changed 24d ago A SkillSpector: pass 32 tokens
original MIT
docs
04Skill Codex
Audit documentation and developer experience against the live product — drift, onboarding, error messages — and write or fix docs when asked.
not rated 346
+1
changed 24d ago A SkillSpector: warn 27 tokens
original MIT
fix
05Skill Codex
Resolve blocking review gaps through bounded repairs and independent re-review; diagnose stalled attempts without expanding scope.
not rated 346
+1
changed 19d ago A SkillSpector: pass 21 tokens
original MIT
genie-hacks
06Skill Codex
Browse, search, and contribute community hacks — real-world patterns for provider switching, teams, skills, hooks, cost optimization, and more.
not rated 346
+1
changed 29d ago A SkillSpector: pass 33 tokens
original MIT
genie
07Skill Codex
Route Genie questions, operations, bugs, and planned work. Resume related wishes; handle ordinary requests directly unless Genie planning or coordination adds value.
not rated 346
+1
changed today A SkillSpector: pass 31 tokens
original MIT
refine
08Skill Codex
Improve a prompt using official OpenAI or Claude guidance. Text or @file mode; --for openai or --for claude selects guidance, not a runtime model.
not rated 346
+1
changed 13d ago A SkillSpector: pass 37 tokens
original MIT
report
09Skill Codex
Investigate a failure to its root cause with grounded evidence, hand the diagnosis to fix, and create a GitHub issue only when asked.
not rated 346
+1
changed 19d ago A SkillSpector: pass 30 tokens
original MIT
review
10Skill Codex
Independently assess designs, plans, implementations, PRs, or repository quality; return evidence and SHIP, FIX-FIRST, or BLOCKED without applying fixes.
not rated 346
+1
changed 19d ago A SkillSpector: pass 35 tokens
original MIT
wish
11Skill Codex
Deliver one decided task end to end — admit it, work it in one worktree, gate, independent review, bounded repair, a merge-ready PR — or plan a multi-group wish when it is bigger than one task.
not rated 346
+1
changed 10d ago A SkillSpector: pass 47 tokens
original MIT
work
12Skill Codex
Execute an approved wish in dependency order with scoped workers, independent review, bounded repairs, and verified completion.
not rated 346
+1
changed today A SkillSpector: pass 23 tokens
original MIT
authoring
13Skill Codex
Write or revise a Genie skill so it survives the shipped contract — frontmatter, house size, starter card, and runtime-neutral voice.
not rated 346
+1 today A 30 tokens
original MIT
merge
14Skill Codex
Resolve an in-progress merge or rebase by the intent of both sides, re-run the full gate on the merged tree, and finish the operation.
not rated 346
+1
changed 13d ago A 32 tokens
original MIT
research
15Skill Codex
Investigate a question against primary sources, cite every claim, and write the findings into the repository's own notes.
not rated 346
+1
changed 24d ago A 25 tokens
original MIT
skill-audit
16Skill Codex
Audit the shipped skill catalogue for overlap, staleness, and drift against the install record, and propose keep, improve, merge, or retire per skill.
not rated 346
+1
changed 24d ago A 36 tokens
original MIT
verify
17Skill Codex
Prove a completion claim with fresh evidence before making it — the gate's exit code, the real diff, the remote's checks, the reviewer's verdict.
not rated 346
+1
changed 24d ago A 34 tokens
original MIT
workfly
18Skill Codex
Discover a procedure and build its saved workflow — dynamic discovery, drafted script, adversarial verification, landed in the catalog.
not rated 346
+1
changed 24d ago A 27 tokens
original MIT
deslop
19Skill Codex
Clean up the prose, code or interface already in scope — protect its meaning, voice and behaviour, remove what only adds reading work, and return findings instead of edits when a review was asked for.
not rated 346
+1 today A 43 tokens
original MIT
mikro
20Plugin Claude Code
Bundles 2 skills, 1 MCP server · 461 tokens together
Registers the mikro MCP server against the current project, so every agent.yaml microagent in the workspace becomes a callable tool.
not rated 346
+1 today A
tokens not measured
original MIT
analyze
21Agent Claude Code
System analysis and focused investigations (universal framework).
not rated 92 10mo ago A 13 tokens
original Apache-2.0
forge
22Agent Claude Code
Universal forge orchestrator - breaks wishes into execution groups with task files and validation (all domains).
not rated 92 10mo ago A 21 tokens
original Apache-2.0
Agent Claude Code
Individual PR executor for garbage-collection fixes - implements.
not rated 92 10mo ago A 15 tokens
original Apache-2.0
Agent Claude Code
Autonomous documentation quality assurance - detect bloat.
not rated 92 10mo ago A 15 tokens
original Apache-2.0
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: